© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51822
    Prev
    Next
    INDEX
    Explanations

    embellished with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ²IJæµ´
    -0.10
    åIJ®
    -0.10
    åIJĦç§įåIJĦæł·
    -0.09
    à¹Ģà¸ķ
    -0.09
    æīĢèĥ½
    -0.09
    çĤķ
    -0.09
    ãģĻãģİãģ¦
    -0.09
    åIJij社ä¼ļ
    -0.09
    毡
    -0.08
    çĵ¤
    -0.08
    POSITIVE LOGITS
    æŀIJ
    0.10
    çĶ³è¯·äºº
    0.08
    èīº
    0.08
    æĬĢæľ¯åĴĮ
    0.08
    emonic
    0.08
    æĥ°
    0.08
     Spot
    0.08
    æĸij
    0.08
    ç»ĨèĬĤ
    0.08
    éĩĬ
    0.08
    Activations Density 0.046%

    No Known Activations